Machine Learning Schemes for Anomaly Detection in Solar Power Plants

Ibrahim, Mariam; Alsheikh, Ahmad; Awaysheh, Feras M.; Alshehri, Mohammad Dahman

doi:10.3390/en15031082

Cited by 58 publications

(16 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Analysis of a single-edge device has the potential to accommodate 512 solar panels within a minute. Moreover, Ibrahim et al [ 20 ] conducted a study to evaluate the efficacy of three established anomaly detection algorithms, namely Autoencoder LSTM (AE-LSTM), Facebook-Prophet, and isolation forest, in detecting anomalies on PV components. The assessment attained a maximum accuracy of 0.896.…”

Section: Literature Reviewmentioning

confidence: 99%

Intelligent IoT Platform for Multiple PV Plant Monitoring

Utama

Pamungkas

Faridh

et al. 2023

Sensors

View full text Add to dashboard Cite

Due to the accelerated growth of the PV plant industry, multiple PV plants are being constructed in various locations. It is difficult to operate and maintain multiple PV plants in diverse locations. Consequently, a method for monitoring multiple PV plants on a single platform is required to satisfy the current industrial demand for monitoring multiple PV plants on a single platform. This work proposes a method to perform multiple PV plant monitoring using an IoT platform. Next-day power generation prediction and real-time anomaly detection are also proposed to enhance the developed IoT platform. From the results, an IoT platform is realized to monitor multiple PV plants, where the next day’s power generation prediction is made using five types of AI models, and an adaptive threshold isolation forest is utilized to perform sensor anomaly detection in each PV plant. Among five developed AI models for power generation prediction, BiLSTM became the best model with the best MSE, MAPE, MAE, and R2 values of 0.0072, 0.1982, 0.0542, and 0.9664, respectively. Meanwhile, the proposed adaptive threshold isolation forest achieves the best performance when detecting anomalies in the sensor of the PV plant, with the highest precision of 0.9517.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Intelligent IoT Platform for Multiple PV Plant Monitoring

Utama

Pamungkas

Faridh

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Multiple previous studies have suggested anomaly detection systems for solar power plants. An anomaly detection system based on autoencoder long short-term memory (AE-LSTM), the Facebook-Prophet, and Isolation Forest were designed to identify anomalies in the electricity generation of solar power plants [11]. An artificial neural network (ANN)-based anomaly detection system has been suggested that can predict and maintain the electricity generation of a solar power plant [12], and another method has been proposed to verify a specific outlier and its candidate for processed data on electricity generation by utilizing correlation analysis of the attribute values for solar power generation and its K-nearest neighbors (K-NN) [13].…”

Section: Related Workmentioning

confidence: 99%

“…Table 7 compares the performance of existing anomaly detection models used in solar power plants and our new model. Ibrahim [11] proposed anomaly detection for PV systems using AC power, yield, and temperature. Anomaly detection models were then developed using AE-LSTM, Facebook-Prophet, and Isolation Forest.…”

Section: Classification Algorithm and Clustering Algorithm For Data T...mentioning

confidence: 99%

Solar Power Plant Network Packet-Based Anomaly Detection System for Cybersecurity

Lee,

Shin,

Seo

2023

CMC

View full text Add to dashboard Cite

As energy-related problems continue to emerge, the need for stable energy supplies and issues regarding both environmental and safety require urgent consideration. Renewable energy is becoming increasingly important, with solar power accounting for the most significant proportion of renewables. As the scale and importance of solar energy have increased, cyber threats against solar power plants have also increased. So, we need an anomaly detection system that effectively detects cyber threats to solar power plants. However, as mentioned earlier, the existing solar power plant anomaly detection system monitors only operating information such as power generation, making it difficult to detect cyberattacks. To address this issue, in this paper, we propose a network packet-based anomaly detection system for the Programmable Logic Controller (PLC) of the inverter, an essential system of photovoltaic plants, to detect cyber threats. Cyberattacks and vulnerabilities in solar power plants were analyzed to identify cyber threats in solar power plants. The analysis shows that Denial of Service (DoS) and Manin-the-Middle (MitM) attacks are primarily carried out on inverters, aiming to disrupt solar plant operations. To develop an anomaly detection system, we performed preprocessing, such as correlation analysis and normalization for PLC network packets data and trained various machine learning-based classification models on such data. The Random Forest model showed the best performance with an accuracy of 97.36%. The proposed system can detect anomalies based on network packets, identify potential cyber threats that cannot be identified by the anomaly detection system currently in use in solar power plants, and enhance the security of solar plants.

show abstract

“…The AE-LSTM was the most accurate model in distinguishing normal and abnormal PV system behavior. The correlation coefficients between the plant's internal and external feature parameters were calculated and used to assess the effectiveness of ML models in detecting anomalies (Ibrahim et al, 2022). However, the model does not apply to large-scale systems.…”

Section: Unsupervised Algorithmsmentioning

confidence: 99%

Anomaly Detection in Renewable Energy Big Data Using Deep Learning

Katamoura,

Aksoy

2023

International Journal of Intelligent Information Technologies

View full text Add to dashboard Cite

This work aims to review the literature on anomaly detection (AD) in renewable energy. Due to the significance of the RE data quality and sensor performance, it is crucial to ensure that the measurement device works correctly and maintains data accuracy. The review identifies the relevant studies on big data anomaly detection in the energy field and synthesizes the related techniques. Also, the study shows a need for segmentation annotations for solar system electroluminescence imagery complicating the domain development of anomaly segmentation approaches. Consequently, most processes create machine learning (ML) models using semi-supervised techniques. Still, these approaches need more generalization regarding variation in environmental or systematic conditions. Furthermore, the studies discussed here focus on existing algorithms that used big data and AD to propose an improved analysis framework. Finally, the work presents a framework to solve the problem of identifying sensors' issues that will appear in data anomalies.

show abstract

Machine Learning Schemes for Anomaly Detection in Solar Power Plants

Cited by 58 publications

References 41 publications

Intelligent IoT Platform for Multiple PV Plant Monitoring

Intelligent IoT Platform for Multiple PV Plant Monitoring

Solar Power Plant Network Packet-Based Anomaly Detection System for Cybersecurity

Anomaly Detection in Renewable Energy Big Data Using Deep Learning

Contact Info

Product

Resources

About